A Framework for Designing Unsupervised Pothole Detection by Integrating Feature Extraction Using Deep Recurrent Neural Network

One of the significant causes of road accidents is the presence of potholes. In order to overcome this difficulty, several techniques have been designed, from manual reporting to authorities taking steps for auto-detection of pothole regions. Traditional techniques related to pothole detection fail in terms of risk during weather variations, high setup cost and no provision for night vision due to the lack of development in effective automatic pothole detection models effectively. The main objective of this work  is to design an automatic pothole detection model for identifying potholes at the earliest time period. To make the processing more manageable and improvise the detection performance, an optimized deep recurrent neural network (ODRNN) is proposed. The pothole detection model consists of three phases, pre-processing, feature extraction and unsupervised classification. Initially, the the set of images are gathered to make a dataset. The first phase is responsible for image enhancement which performs input image resizing, background noise removal utilizing median filter approach and RGB to grey scale conversion. The second phase is responsible for extracting the most relevant characteristics of the pothole region using Shape-based feature extraction approach. In the final phase, the extracted features are classified with ODRNN. To enhance the efficiency of conventional RNNs, the weight values of the classifier are optimized using the Improved Atom search optimization algorithm (IASO). It classifies the pothole and non-pothole region with a lesser error function, implemented and tested experimentally in terms of accuracy, recall, precision and error performance. This work provides better performance with a maximum accuracy of 97.7% to become a better strategy for pothole detection.